© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25269
    Prev
    Next
    INDEX
    Explanations

    code callbacks and actions

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is spotting programming‐style identifiers (function names, type/event names, macros) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     our
    -1.26
     bizim
    -1.14
     Некоторые
    -1.05
    typo
    -0.96
    accessoires
    -0.93
     compleja
    -0.93
     també
    -0.92
     schilder
    -0.91
    restes
    -0.89
    ervous
    -0.88
    POSITIVE LOGITS
     who
    0.98
    Ｌ
    0.96
     when
    0.91
     questione
    0.89
     מצ
    0.89
     Brasília
    0.88
    ‚¬
    0.87
     adiv
    0.87
     pv
    0.86
    ყ
    0.86
    Activations Density 0.022%

    No Known Activations